A hybrid approach to boost the permutation index for similarity searching

We propose a hybrid strategy that combines three ideas, namely, a convenient way for reducing the length of the permutations, using a permutation similarity measure adjusted for these clipped permutations, and the use of the closest permutant of each object as a pivot for it. In this way, we increas...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Figueroa, Karina, Camarena Ibarrola, Antonio, Reyes, Nora Susana, Paredes, Rodrigo, Hernandez Martinez, Braulio Ramses
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2022
Materias:
Ciencias Informáticas
Similariy search
Permutant-based index
Permutation similarity measures
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/149649
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-149649
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Similariy search
Permutant-based index
Permutation similarity measures
spellingShingle Ciencias Informáticas
Similariy search
Permutant-based index
Permutation similarity measures
Figueroa, Karina
Camarena Ibarrola, Antonio
Reyes, Nora Susana
Paredes, Rodrigo
Hernandez Martinez, Braulio Ramses
A hybrid approach to boost the permutation index for similarity searching
topic_facet Ciencias Informáticas
Similariy search
Permutant-based index
Permutation similarity measures
description We propose a hybrid strategy that combines three ideas, namely, a convenient way for reducing the length of the permutations, using a permutation similarity measure adjusted for these clipped permutations, and the use of the closest permutant of each object as a pivot for it. In this way, we increase the discriminability of the permutation index in order to reduce even more the number of distance computations without reducing the answer quality. The performance of our proposal is tested using two classical real-world databases: NASA and Colors which are part of the SISAP project’s metric space benchmark. We reduced more than 30% of the number of distance evaluations needed to solve the queries on both databases.
format Objeto de conferencia
Objeto de conferencia
author Figueroa, Karina
Camarena Ibarrola, Antonio
Reyes, Nora Susana
Paredes, Rodrigo
Hernandez Martinez, Braulio Ramses
author_facet Figueroa, Karina
Camarena Ibarrola, Antonio
Reyes, Nora Susana
Paredes, Rodrigo
Hernandez Martinez, Braulio Ramses
author_sort Figueroa, Karina
title A hybrid approach to boost the permutation index for similarity searching
title_short A hybrid approach to boost the permutation index for similarity searching
title_full A hybrid approach to boost the permutation index for similarity searching
title_fullStr A hybrid approach to boost the permutation index for similarity searching
title_full_unstemmed A hybrid approach to boost the permutation index for similarity searching
title_sort hybrid approach to boost the permutation index for similarity searching
publishDate 2022
url http://sedici.unlp.edu.ar/handle/10915/149649
work_keys_str_mv AT figueroakarina ahybridapproachtoboostthepermutationindexforsimilaritysearching
AT camarenaibarrolaantonio ahybridapproachtoboostthepermutationindexforsimilaritysearching
AT reyesnorasusana ahybridapproachtoboostthepermutationindexforsimilaritysearching
AT paredesrodrigo ahybridapproachtoboostthepermutationindexforsimilaritysearching
AT hernandezmartinezbraulioramses ahybridapproachtoboostthepermutationindexforsimilaritysearching
AT figueroakarina hybridapproachtoboostthepermutationindexforsimilaritysearching
AT camarenaibarrolaantonio hybridapproachtoboostthepermutationindexforsimilaritysearching
AT reyesnorasusana hybridapproachtoboostthepermutationindexforsimilaritysearching
AT paredesrodrigo hybridapproachtoboostthepermutationindexforsimilaritysearching
AT hernandezmartinezbraulioramses hybridapproachtoboostthepermutationindexforsimilaritysearching
bdutipo_str Repositorios
_version_ 1764820461778108419

Ejemplares similares